About the athrun zala tag
athrun zala is a character tag that NovelAI Diffusion can use. On Danbooru it has 811 posts, and its best-rated still image scores 100. The samples above put the tag at the front of a fixed base prompt with seed 1234, so the differences between tags come from the tag alone.
How each model draws athrun zala
Follows composition and expression instructions closely, so the effect shows in a tidy form.
Reacts to the tag more strongly, so its effect is easier to see.
WAI illustrious SDXL v17, a local model. Shows how the same tag reads outside NovelAI.
Writing athrun zala in a prompt
Put the subject first, then this tag, then quality tags.
athrun zala, solo, best quality, masterpiecewlop, athrun zala, soloThe negative prompt and the full settings are on the terms page.
How these samples were made
Every image uses 832×1216, seed 1234, 23 steps and the k_euler_ancestral sampler. The base prompt and negative prompt stay the same for every tag, and only the tag under test changes. Images flagged by the NSFW check are regenerated with a new seed or hidden.
From the Danbooru wiki
Show the wiki text ▾Hide ▴
Athrun Zala is the deuteragonist of both Gundam SEED and Gundam SEED Destiny. He has blue hair and green eyes. Childhood friend and best friend of Kira Yamato. [spoilers]Becomes the boyfriend of Cagalli Yula Athha.[/spoilers]
He pilots the Aegis Gundam and the Justice Gundam in Gundam SEED, the Saviour Gundam and the Infinite Justice Gundam in Gundam SEED Destiny, and a Z'Gok in Gundam SEED Freedom, [spoilers]which in reality, is a disguised form of his upgraded Infinite Justice Gundam Type II.[/spoilers]
FAQ
Does NovelAI recognize athrun zala?
Compare the samples on this page. Every tag on this site shares the same seed and base prompt, so any change you see comes from athrun zala.
How do I write athrun zala in a prompt?
Write "athrun zala" near the front of the prompt and separate it from other tags with commas.
Should I use V5 or V4.5?
V4.5 shows the tag's effect more strongly. V5 gives steadier images with fewer artifacts.